Teaching-system episode framework: knowing–teaching–acting across three capability surfaces¶
Research Method · All research methods
Evidence · 2 claims (2 for) · 1 study (1 design),q2· 0 of 1 report an effect size · 2 claims rest on one study
Description¶
The article proposes that tutor-agent readiness requires three separable capability surfaces: Stage 1 pedagogical judgment (a bounded teacher decision from packaged evidence), Stage 2 situated tutoring (a history-dependent adaptive teaching policy over a multi-turn episode), and Stage 3 end-to-end LMS workflow execution (institutional action). It argues these "separate knowing what a teacher should do, teaching through an evolving interaction, and acting without losing the educational rationale across an institutional workflow." The framework defines an auditable teaching-system episode in which evidence supports a decision, the decision guides interaction or execution, and the learner or course consequence is observable, spanning six teacher-work capabilities: diagnosing, designing, creating, teaching, communicating, and evaluating.
Accounts¶
- Teaching-system episode framework: knowing–teaching–acting across three capability surfaces: The article proposes that tutor-agent readiness requires three separable capability surfaces: Stage 1 pedagogical judgment (a bounded teacher decision from packaged evidence), Stage 2 situated tutoring (a history-dependent adaptive teaching policy over a multi-turn episode), and Stage 3 end-to-end LMS workflow execution (institutional action). It argues these "separate knowing what a teacher should do, teaching through an evolving interaction, and acting without losing the educational rationale across an institutional workflow." The framework defines an auditable teaching-system episode in which evidence supports a decision, the decision guides interaction or execution, and the learner or course consequence is observable, spanning six teacher-work capabilities: diagnosing, designing, creating, teaching, communicating, and evaluating. (Zixin Chen et al. (2026))
Claims¶
- Across 17 frontier models, Stage 1 pedagogical-judgment scores are high (mean 0.893) while rank correlations with Stage 2 (ρ=0.24) and Stage 3 (ρ=0.21) are weak, with workflow scores topping out at 0.704 [+M]
- Claude Opus 4.8 has the highest overall score (0.803) and is the only model ranking in the top three on all three stages, yet does not saturate situated tutoring (0.773) or workflows (0.704) [+W]
Related Research Methods¶
-
Key Sources¶
- Zixin Chen, Peng Liu, Rui Sheng, Haobo Li, Jianhong Tu, Xiaodong Deng, Kashun Shum, Dayiheng Liu, Huamin Qu. (2026). Are Agents Ready to Teach? A Multi-Stage Benchmark for Real-World Teaching Workflows. Preprint. https://arxiv.org/abs/2605.14322
Page metadata
| Field | Value |
|---|---|
type |
research-method |
id |
teaching-system-episode-framework-knowingteachingacting-across-three-capability-surfaces |
title |
Teaching-system episode framework: knowing–teaching–acting across three capability surfaces |
description |
The article proposes that tutor-agent readiness requires three separable capability surfaces: Stage 1 pedagogical judgment (a bounded teacher decision from packaged evidence), Stage 2 situated tutoring (a history-dependent adaptive teaching policy over a multi-turn episode), and Stage 3 end-to-end L |
status |
review |
generated |
by process:settle-candidates on 2026-10-10 |
trust |
unverified — no one has confirmed this page's content |
Frontmatter is the page's machine-readable record — see the Schema & Guide.